blob: 68f4600f1d3909f2a8930cb8a1606dfde0dfdb10 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
|
//===-- AMDGPUTargetTransformInfo.cpp - AMDGPU specific TTI pass ---------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// \file
// This file implements a TargetTransformInfo analysis pass specific to the
// AMDGPU target machine. It uses the target's detailed information to provide
// more precise answers to certain TTI queries, while letting the target
// independent and default TTI implementations handle the rest.
//
//===----------------------------------------------------------------------===//
#include "AMDGPUTargetTransformInfo.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/CostTable.h"
#include "llvm/Target/TargetLowering.h"
using namespace llvm;
#define DEBUG_TYPE "AMDGPUtti"
void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L,
TTI::UnrollingPreferences &UP) {
UP.Threshold = 300; // Twice the default.
UP.MaxCount = UINT_MAX;
UP.Partial = true;
// TODO: Do we want runtime unrolling?
for (const BasicBlock *BB : L->getBlocks()) {
for (const Instruction &I : *BB) {
const GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(&I);
if (!GEP || GEP->getAddressSpace() != AMDGPUAS::PRIVATE_ADDRESS)
continue;
const Value *Ptr = GEP->getPointerOperand();
const AllocaInst *Alloca = dyn_cast<AllocaInst>(GetUnderlyingObject(Ptr));
if (Alloca) {
// We want to do whatever we can to limit the number of alloca
// instructions that make it through to the code generator. allocas
// require us to use indirect addressing, which is slow and prone to
// compiler bugs. If this loop does an address calculation on an
// alloca ptr, then we want to use a higher than normal loop unroll
// threshold. This will give SROA a better chance to eliminate these
// allocas.
//
// Don't use the maximum allowed value here as it will make some
// programs way too big.
UP.Threshold = 800;
}
}
}
}
unsigned AMDGPUTTIImpl::getNumberOfRegisters(bool Vec) {
if (Vec)
return 0;
// Number of VGPRs on SI.
if (ST->getGeneration() >= AMDGPUSubtarget::SOUTHERN_ISLANDS)
return 256;
return 4 * 128; // XXX - 4 channels. Should these count as vector instead?
}
unsigned AMDGPUTTIImpl::getRegisterBitWidth(bool) { return 32; }
unsigned AMDGPUTTIImpl::getMaxInterleaveFactor() {
// Semi-arbitrary large amount.
return 64;
}
|
